• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 2005.05a
• /
• pp.795-797
• /
• 2005

During the past few years, various traffic-flow forecasting models, i.e. an ARIMA, an ANN, and so on, have been developed to predict more accurate traffic flow. However, these models analyze historical data in an attempt to predict future value of a variable of interest. They make use of the following basic strategy. Past data are analyzed in order to identify a pattern that can be used to describe them. Then this pattern is extrapolated, or extended, into the future in order to make forecasts. This strategy rests on the assumption that the pattern that has been identified will continue into the future. So ARIMA or ANN models with its traditional architecture cannot be expected to give good predictions unless this assumption is valid; The statistical models in particular, the time series models are deficient in the sense that they merely extrapolate past patterns in the data without reflecting the expected irregular and infrequent future events Also forecasting power of a single model is limited to its accurate. In this paper, we compared with an ANN model and ARIMA model and tried to combine an ARIMA model and ANN model for obtaining a better forecasting performance. In addition to combining two models, we also introduced judgmental adjustment technique. Our approach can improve the forecasting power in traffic flow. To validate our model, we have compared the performance with other models. Finally we prove that the proposed model, i.e. ARIMA + ANN + Judgmental Adjustment, is superior to the other model.

• The Journal of the Acoustical Society of Korea
• /
• v.13 no.6
• /
• pp.5-14
• /
• 1994

This paper is about an experiment of speaker-independent automatic Korean spoken words recognition using Multi-Layered Perceptron and Error Back-propagation algorithm. The object words are 50 citynames of D.D.D local numbers. 43 of those are 2 syllables and the rest 7 are 3 syllables. The words were not segmented into syllables or phonemes, and some feature components extracted from the words in equal gap were applied to the neural network. That led independent result on the speech duration, and the PARCOR coefficients calculated from the frames using linear predictive analysis were employed as feature components. This paper tried to find out the optimum conditions through 4 differerent experiments which are comparison between total and pre-classified training, dependency of recognition rate on the number of frames and PAROCR order, recognition change due to the number of neurons in the hidden layer, and the comparison of the output pattern composition method of output neurons. As a result, the recognition rate of $89.6\%$ is obtaimed through the research.

• Journal of the Korea Computer Industry Society
• /
• v.6 no.2
• /
• pp.279-286
• /
• 2005

The prefabricated type used generally in Korea to join cable runs on new installations or to repair broken Cable runs on existing installations, because installation is very simple and save time. This type is a permanent, shielded and submersible cable joint for direct burial or vault application. It confirms to the requirements of IEEE std. 404-1993 by factory testing, but many problems of insulated cable systems are caused by internal defects of the joint part which have to be mounted ensile. Faults arise from impurities or voids. A suitable solution for a monitoring of cable joints during the after-laying test and service is partial discharge detection. <중략> $\Phi-q-n$ properties were measured using detection impedance, high pass filter and computerized data acquisition system. Statistic Value like maximum charge, repetition rate, average charge, etc. are calculated. It is possible to quantitative analysis of $\Phi-q-n$ properties from this statistic value and pattern analysis.

• Journal of Internet Computing and Services
• /
• v.6 no.1
• /
• pp.105-114
• /
• 2005

This paper describes a new measuring technique by analysing multiple time-series patterns. This paper's goal is that extracts a really measured value having a sample pattern which is the best matched with an inputted time-series, and calculates a difference ratio with the value. Therefore, the proposed technique is not a recognition but a measurement. and not a hardware but a software. The proposed technique is consisted of three stages, initialization, learning and measurement. In the initialization stage, it decides weights of all parameters using importance given by an operator. In the learning stage, it classifies sample patterns using LBG and DTW algorithm, and then creates code sequences for all the patterns. In the measurement stage, it creates a code sequence for an inputted time-series pattern, finds samples having the same code sequence by hashing, and then selects the best matched sample. Finally it outputs the really measured value with the sample and the difference ratio. For the purpose of performance evaluation, we tested on multiple time-series patterns obtained from etching machine which is a semiconductor manufacturing.

• Journal of the Korea Convergence Society
• /
• v.11 no.6
• /
• pp.1-6
• /
• 2020

In this study, research on character recognition, which is one of the fields of computer vision, was conducted. Optical character recognition, which is one of the most widely used character recognition techniques, suffers from decreasing recognition rate if the recognition target deviates from a certain standard and format. Hence, this study aimed to address this limitation by applying deep learning techniques to character recognition. In addition, as most character recognition studies have been limited to English or number recognition, the recognition range has been expanded through additional data training on Korean text. As a result, this study derived a deep learning-based character recognition algorithm for Korean text recognition. The algorithm obtained a score of 0.841 on the 1-NED evaluation method, which is a similar result to that of English recognition. Further, based on the analysis of the results, major issues with Korean text recognition and possible future study tasks are introduced.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.10 no.4
• /
• pp.257-267
• /
• 2017

Compressed Sensing(CS) deals with linear inverse problems. The theoretical results of CS have had an impact on inference problems and presented amazing research achievements in the related fields including signal processing and information theory. However, in order for CS to be applied in practical environments, there are two significant challenges to be solved. One is to guarantee in real time recovery of CS signals, and the other is that the signals have to be sparse. To this end, the latest researches using deep learning technology have emerged. In this paper, we consider CS problems based on deep learning and discuss the latest research results. And the approaches for CS signal reconstruction using deep learning show superior results in terms of recovery time and performance. It is expected that the approaches for CS reconstruction using deep learning shown in recent studies can not only raise the possibility of utilization of CS, but also be highly exploited in the fields of signal processing and communication areas.

• Journal of Electrical Engineering and Technology
• /
• v.12 no.6
• /
• pp.2388-2398
• /
• 2017

In this study, we propose a robust face recognition system to pose variations based on automatic pose estimation. Radial basis function neural network is applied as one of the functional components of the overall face recognition system. The proposed system consists of preprocessing and recognition modules to provide a solution to pose variation and high-dimensional pattern recognition problems. In the preprocessing part, principal component analysis (PCA) and 2-dimensional 2-directional PCA ($(2D)^2$ PCA) are applied. These functional modules are useful in reducing dimensionality of the feature space. The proposed RBFNNs architecture consists of three functional modules such as condition, conclusion and inference phase realized in terms of fuzzy "if-then" rules. In the condition phase of fuzzy rules, the input space is partitioned with the use of fuzzy clustering realized by the Fuzzy C-Means (FCM) algorithm. In conclusion phase of rules, the connections (weights) are realized through four types of polynomials such as constant, linear, quadratic and modified quadratic. The coefficients of the RBFNNs model are obtained by fuzzy inference method constituting the inference phase of fuzzy rules. The essential design parameters (such as the number of nodes, and fuzzification coefficient) of the networks are optimized with the aid of Particle Swarm Optimization (PSO). Experimental results completed on standard face database -Honda/UCSD, Cambridge Head pose, and IC&CI databases demonstrate the effectiveness and efficiency of face recognition system compared with other studies.

• Journal of Korea Multimedia Society
• /
• v.6 no.1
• /
• pp.136-147
• /
• 2003

To achieve an optimal performance for a given problem, we need an integrative process of the parameter optimization via learning and the structure optimization via model selection. In this paper, we propose an efficient optimization method for improving generalization performance by considering the property of each sub-method and by combining them with common theoretical properties. First, weight parameters are optimized by natural gradient teaming with adaptive regularization, which uses a diverse error function. Second, the network structure is optimized by eliminating unnecessary parameters with natural pruning. Through iterating these processes, candidate models are constructed and evaluated based on the Bayesian Information Criterion so that an optimal one is finally selected. Through computational experiments on benchmark problems, we confirm the weight parameter and structure optimization performance of the proposed method.

• Journal of Korea Multimedia Society
• /
• v.22 no.12
• /
• pp.1415-1429
• /
• 2019

Nowadays object tracking process becoming one of the most challenging task in Computer Vision filed. A CSR-DCF (channel spatial reliability-discriminative correlation filter) tracking algorithm have been proposed on recent tracking benchmark that could achieve stat-of-the-art performance where channel spatial reliability concepts to DCF tracking and provide a novel learning algorithm for its efficient and seamless integration in the filter update and the tracking process with only two simple standard features, HoGs and Color names. However, there are some cases where this method cannot track properly, like overlapping, occlusions, motion blur, changing appearance, environmental variations and so on. To overcome that kind of complications a new modified version of CSR-DCF algorithm has been proposed by integrating deep learning based object detection and CSRT tracker which implemented in OpenCV library. As an object detection model, according to the comparable result of object detection methods and by reason of high efficiency and celerity of Faster RCNN (Region-based Convolutional Neural Network) has been used, and combined with CSRT tracker, which demonstrated outstanding real-time detection and tracking performance. The results indicate that the trained object detection model integration with tracking algorithm gives better outcomes rather than using tracking algorithm or filter itself.

• Journal of Intelligence and Information Systems
• /
• v.7 no.1
• /
• pp.177-197
• /
• 2001

This paper is aimed at proposing a data mining-driven analysis to manage the customer defection rate in the bank. After 1997 IMF crisis, Korean banks were suffering from hard-pressed restructuring. At the heart of such restructuring effects, there was the need to manage the customer more effectively than ever. So far, many banks in Korea used to a poor management of customers without any highly-skillful techniques. In line with this argument, we propose several data mining techniques to determine more effective technique far managing customer deflection. We applied three data mining techniques such as logit model, neural network, and C5.0. Experiment data were collected from personal deposit account data of a specific bank in Korea. After experiments, we found that C5.0 showed more robust performance compared to other two techniques. On the basis of those experiment results, we proposed customer defection management policy.